摘要
城市轨道交通短时客流量受到多种因素综合影响,变化十分复杂。当前模型无法描述城市轨道交通短时客流量的变化特点,预测结果不理想。为了获得理想的预测结果,更加准确地描述城市轨道交通短时客流量变化趋势,提出了深度学习算法的城市轨道交通短时客流量预测模型。首先收集城市轨道交通短时客流量历史数据,引入混沌分析算法对其进行多维空间重构,有效挖掘出变化趋势,然后采用深度学习算法拟合城市轨道交通短时客流量变化趋势,建立城市轨道交通短时客流量预测模型,最后进行了城市轨道交通短时客流量预测仿真测试。结果表明,深度学习算法的城市轨道交通短时客流量预测精度高,预测误差要小于对比模型。该模型为城市轨道交通短时客流量预测建模提供了一种新的工具。
The short-term passenger flow of urban rail transit is affected by many factors,and the change is very complex. The current model can not describe the change characteristics of short-term passenger flow of urban rail transit,and the prediction results are not ideal. In order to obtain ideal prediction results and more accurately describe the change trend of short-term passenger flow of urban rail transit,A short-term passenger flow prediction model of Urban Rail Transit Based on deep learning algorithm is proposed. Firstly,the historical data of short-term passenger flow of urban rail transit are collected,and the chaotic analysis algorithm is introduced to reconstruct its multi-dimensional space to effectively mine the change trend of force load. Then,the deep learning algorithm is used to fit the change trend of short-term passenger flow of urban rail transit,and the prediction model of short-term passenger flow of urban rail transit is established,Finally,the simulation test of short-term passenger flow prediction of urban rail transit is carried out.The results show that the prediction accuracy of urban rail transit short-term passenger flow based on deep learning algorithm is high,and the prediction error is less than that of the comparison model,which provides a new tool for urban rail transit short-term passenger flow prediction modeling.
作者
任娜
REN Na(Shanxi College of Communication Technology,Xi’an 710018,China)
出处
《系统仿真技术》
2021年第4期259-264,共6页
System Simulation Technology
关键词
城市管理系统
轨道交通
深度学习算法
短时客流量
预测模型
urban management system
rail transit
deep learning algorithm
short term passenger flow
prediction model